Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

User similarity and deviation analysis for adaptive visualizations

: Nazemi, Kawa; Retz, Wilhelm; Kohlhammer, Jörn; Kuijper, Arjan


Yamamoto, S.:
Human interface and the management of information. Information and knowledge design and evaluation. 16th international conference, HCI International 2014. Vol.1 : Heraklion, Crete, Greece, June 22-27, 2014; Proceedings
Berlin: Springer, 2014 (Lecture Notes in Computer Science 8521)
ISBN: 978-3-319-07730-7 (Print)
ISBN: 978-3-319-07731-4 (Online)
International Conference on Human-Computer Interaction (HCI International) <16, 2014, Heraklion>
Fraunhofer IGD ()
adaptive information visualization; machine learning; User Modeling; semantics visualization

Adaptive visualizations support users in information acquisition and exploration and therewith in human access of data. Their adaptation effect is often based on approaches that require the training by an expert. Further the effects often aims to support just the individual aptitudes. This paper introduces an approach for modeling a canonical user that makes the predefined training-files dispensable and enables an adaptation of visualizations for the majority of users. With the introduced user deviation algorithm, the behavior of individuals can be compared to the average user behavior represented in the canonical user model to identify behavioral anomalies. The further introduced similarity measurements allow to cluster similar deviated behavioral patterns as groups and provide them effective visual adaptations.